--- title: "AI ABM: Map and Reach the Whole Buying Committee | Prosyo" description: "Account-based outreach with AI agents: map the buying committee of every target account, find the people by role and run coordinated LinkedIn and email." url: "https://prosyo.com/pt/ai-agents/use-cases/ai-abm-buying-committee/" image: "https://prosyo.com/wp-content/uploads/2026/10/cropped-Prosyo-Icon-Transparent-1.png" language: "pt" --- Research Agent · On demand # AI ABM: reach the whole buying committee of every target account For each target account, the Research Agent maps the buying committee by role, finds the people with your lead data apps and saves one list per role, ready for coordinated outreach. [Start free — 7 days](https://app.prosyo.com/) [Book a demo](https://prosyo.com/pt/) - 7 days free - No card required - Nothing sends without your yes Loved by founders, agencies and sales teams How it runs ## One request. The agent does the rest. Type it to Penny, or use it as the agent’s brief and let it run on its trigger. **Agent Penny***Run with Research Agent* For each company on “ABM Q1 accounts”, find the economic buyer, two champions, one user and one technical evaluator with Apollo. Tag each person with the account and role, and save one list per role. 1. Reads your target accounts 2. Maps the buying committee roles you sell to 3. Finds people for each role with your lead data apps 4. Tags everyone with the account and role 5. Saves one list per role, ready for staggered campaigns Buying committees mapped **Target accounts** 20 **People found** 92 **Lists saved** 5, one per role **Accounts fully covered** 17 of 20 Illustrative run. Sending, paid actions and changes in other apps wait for your yes. The guide Enterprise deals are not won by one contact. Five or more people usually sign off: someone who owns the budget, a champion who feels the pain, the users who will live with the tool, someone from IT or security, and an influencer in ops or finance. Single-threaded deals stall the moment one person goes quiet. Account-based outreach fixes that by reaching the whole committee, in the right order, with a message for each role. AI agents make it practical for more than a handful of accounts. ## How AI changes ABM The hard part of ABM was never the idea. It was the hours: mapping every account, finding the right person for each role, tagging them, and keeping the lists clean. The Research Agent does that mapping from one brief, for 20 accounts or 200, and saves the result in a structure your campaigns can use directly. ## What the agent does It reads your target accounts. For each one, it looks for the roles you named, using Apollo, ZoomInfo or another lead data app you connected, plus LinkedIn. It checks each person against your ideal customer, tags them with the account and role, and saves one list per role, for example “ABM Q1 – Economic buyers” and “ABM Q1 – Champions”. It tells you which accounts it could not fully cover, so you can fill the gaps by hand. If your team maps accounts on a Miro board, it can read the board to see who you already know. ## Run the program 1. Pick 20 to 50 accounts that fit and show timing signals: funding, new leaders, hiring, or visits. 2. Run the agent with the roles your deal needs. 3. Give each list to the Writer with a role-specific brief: outcomes for the economic buyer, team pain for the champion, daily workflow for users. 4. Launch one campaign per role, staggered: champions and users first, economic buyers a week later, technical evaluators with a security or integration resource. ## Keep it coordinated - Use different senders for different levels where you can: a rep for champions, a founder or executive for the economic buyer. - Treat every account as one conversation. When anyone at an account replies, review the others before the next touch. - Have the Reply Agent draft answers with the account brief from your research, so every reply sounds informed. ## Measure the account, not the message In ABM the unit of success is the account. Track how many accounts have at least one conversation, and how many have two or more people engaged. Those numbers predict pipeline far better than reply rates on a single campaign. **Research Agent***AI prospecting agent* **Starts** When you run it **Apps** [Apollo.io](https://prosyo.com/pt/integration/apollo-io/) [ZoomInfo](https://prosyo.com/pt/integration/zoominfo/) [Miro](https://prosyo.com/pt/integration/miro/) **Approval** Sending, paid actions and other apps wait for your yes **Great for** Sales teams, Agencies **Available on** Penny Agents, Penny SDR and Penny SDR All-in [Start free — 7 days](https://app.prosyo.com/) [Book a demo](https://prosyo.com/pt/) - [How the Research Agent works](https://prosyo.com/pt/ai-agents/research-agent/) - [All agent use cases](https://prosyo.com/pt/ai-agents/#use-cases) - [Penny pricing](https://prosyo.com/pt/pricing/#penny) Apps in this use case ## Connected in a click, used on your terms Sign in once. You choose what it may do, and changes wait for your approval. [**Apollo.io**Data Find people and companies, enrich contacts and look up firmographics. Apollo.io + Prosyo](https://prosyo.com/pt/integration/apollo-io/) [**ZoomInfo**Data Search ZoomInfo contacts and companies with your ZoomInfo account. ZoomInfo + Prosyo](https://prosyo.com/pt/integration/zoominfo/) [**Miro**Work/Docs Read and update boards, diagrams and notes in your selected Miro team. Miro + Prosyo](https://prosyo.com/pt/integration/miro/) You stay in control ## Research Agent asks before it acts You choose how much it does alone. Reading and research always run straight away; anything that sends, spends or changes another app waits as a card you approve, unless you allowed it. - **Ask before every step**It asks before every step, unless you allowed that action to run on its own. - **Ask before any change**It reads and researches freely, then brings every change back to you. - **Handle routine work alone**Saving people, tagging and preparing drafts run on their own. Sending, paid actions and other apps still wait. Keep going ## Use cases that pair well with this one [On demandBuild Apollo prospect lists that only hold people who fitPoint the Research Agent at Apollo with a plain-language brief. It finds the people, checks each one against your ideal customer and saves the fits to a Prosyo list, ready for outreach.Research Agent](https://prosyo.com/pt/ai-agents/use-cases/apollo-prospect-lists/)[On demandFind lookalikes of your best paying customersThe Research Agent reads your best customers in Stripe, works out what they have in common, then finds similar companies and people with Apollo and saves the fits to a list.Research Agent](https://prosyo.com/pt/ai-agents/use-cases/lookalike-best-customers/)[High intentReach former champions the moment they change jobsWhen Intent spots a past champion at a new company, the Research Agent finds their new details with Apollo and saves them to a list, so you are first to say congratulations.Research Agent](https://prosyo.com/pt/ai-agents/use-cases/job-change-champions/) [Browse every use case](https://prosyo.com/pt/ai-agents/#use-cases) FAQ ## This use case, answered Straight answers on what the agents do, what they cost and how you stay in control. **Want to see it on your market?** Book a short demo. A real person runs the agents on your own ideal customer. [Book a demo](https://prosyo.com/pt/) **What roles should I map?** Most deals involve an economic buyer, champions, users, a technical evaluator and an influencer such as RevOps or finance. Tell the agent which ones matter for your deal. **Why one list per role?** Each role needs a different message and a different moment. One list per role lets you run coordinated campaigns that reach the champion before the economic buyer. **Do I need a lead database?** It helps. Apollo, ZoomInfo or Lusha make finding the right people per role much faster; LinkedIn alone works for smaller programs. **When does it run?** Whenever you like, or when you ask Penny in chat. If it becomes a weekly habit, put it on a schedule instead and it runs on its own. **Which apps does it use, and do I need accounts?** It uses Apollo.io, with one-click sign-in; ZoomInfo, with one-click sign-in; Miro, with one-click sign-in. Each app works with your own access, so the agent only sees what your account can see, and anything an app charges for is billed by that app. **Can the agent act without my approval?** Reading and research run straight away. Routine work such as saving people to a list or tagging can run alone if you allow it. Sending, paid actions and changes in other apps wait for your yes unless you explicitly allowed that action. **What does a run cost?** Each step uses AI credits like a Penny question, and you set a spending cap for each run. If a run reaches its cap, it waits for you. Paid actions such as enrichment, and charges from connected apps, are separate. **Can I change what the agent does?** Yes, in plain words. Edit the brief, attach a skill such as your own playbook, tick or untick apps and change what needs approval. The next run follows the new instructions, and finished work stays saved. **Which agent runs it, and what pairs well with it?** The Research Agent, Prosyo’s ai prospecting agent. Start from its template and use this request as the brief. It pairs well with the Qualifier Agent and the Writer Agent, which can pick up its results through your lists and inbox. **How do I see what the agent did?** Every run comes with a plain-English report of what it did, what it cost and anything waiting for you. Results show as formatted answers, tables or diagrams, and you get a notification when a run finishes or needs your approval. **Which Prosyo plan do I need?** Agents come with the Penny Agents, Penny SDR and Penny SDR All-in plans: 5, 10 or 20 agents. Every workspace starts with a 7-day free trial, no card required. ## Your next 10 meetings are already on LinkedIn. 7 days free, no card. Pay later and change your mind? Full refund within 7 days. [Start free — 7 days](https://app.prosyo.com/) [See pricing](https://prosyo.com/pricing/) - 7 days free - No card required - Cancel in two clicks